Knowledge catalogue
arXiv:2609.38766v1 Announce Type: new Abstract: Scientific agents can retrieve relevant passages yet still lose functional order, mix evidence across sources, or state conclusions that exceed the retr
arXiv:2609.39420v1 Announce Type: new Abstract: Large language models are strong general-purpose code generators, but executable algorithmic trading remains a demanding specialization target: a model
arXiv:2609.38974v1 Announce Type: new Abstract: Large language models are reshaping ecommerce from static recommenders into interactive shopping assistants, yet real-world shopping requires session-le
arXiv:2609.39363v1 Announce Type: cross Abstract: Multi-image understanding requires MLLMs not only to recognise the content of individual images, but also to organise visual evidence distributed acro
arXiv:2609.38884v1 Announce Type: cross Abstract: Optimization modeling formulates real-world decision problems as mathematical programs that solvers can use to find optimal decisions. Large language
arXiv:2609.39304v1 Announce Type: cross Abstract: When an off-the-shelf coding agent is used directly as a robot policy, observing a browser-based 3D interface through screenshots and acting by posing
arXiv:2609.38309v1 Announce Type: cross Abstract: The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating
arXiv:2609.38574v1 Announce Type: new Abstract: Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the n
arXiv:2609.38670v1 Announce Type: new Abstract: Final-answer accuracy does not reveal whether a scientific-search agent failed to encounter a target paper, attempt to inspect it, or return an accepted
arXiv:2609.38161v1 Announce Type: new Abstract: Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We
arXiv:2609.36488v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong performance on complex web navigation tasks, yet they remain brittle in real-world settings w
arXiv:2609.32754v2 Announce Type: replace Abstract: Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequ
arXiv:2602.20144v2 Announce Type: replace-cross Abstract: We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP)
arXiv:2609.36848v1 Announce Type: new Abstract: Human Activity Recognition (HAR) through wearable sensors greatly improves the quality of human life through its multiple applications. For HAR, multi-s
arXiv:2609.36228v1 Announce Type: new Abstract: The EU AI Act introduces extensive compliance requirements for organizations that develop, deploy, or integrate AI systems. Many of these requirements a
arXiv:2609.35820v1 Announce Type: cross Abstract: English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce au-Multilingual, extending au-Voice to Spanish, Brazilian Por
arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,
arXiv:2609.36820v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advantages by centering and normalizing
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s
A new report out today from Google LLC’s Google Threat Intelligence Group finds that monthly software vulnerability disclosures doubled between January and August. Not surprisingly, artificial intelli
arXiv:2609.37053v1 Announce Type: new Abstract: Multimodal GUI agents have achieved impressive results on general software benchmarks, yet their ability to operate professional scientific software rem
arXiv:2609.36838v1 Announce Type: cross Abstract: Visual agents solve problems by interleaving reasoning with image operations, and on-policy distillation (OPD) provides guidance from a strong teacher
arXiv:2609.36210v1 Announce Type: cross Abstract: Generative denoising models, such as diffusion and flow-matching, learn to sample from complex distributions by training a deep neural network denoise
PDFs aren't built for machines: text shows up as glyphs with coordinates, tables as line segments instead of table structures. @jerryjliu0, CEO of LlamaIndex, digs into what that means for AI agents i
arXiv:2609.35816v1 Announce Type: cross Abstract: Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional
arXiv:2609.38072v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote sensing visual question answering (VQA) requires models to resolve small visual evidence within extremely large image
arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template
arXiv:2609.37082v1 Announce Type: new Abstract: Long-horizon information-seeking agents often accumulate noisy or misleading context, causing early mistakes to persist and making recovery increasingly
arXiv:2609.34683v1 Announce Type: new Abstract: The optimization of LLM serving engines, such as vLLM and SGLang, is largely benchmark-driven: optimizations, scheduling policies, hardware and system d
arXiv:2609.33117v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-v
Artificial intelligence is changing the makeup of internet traffic, making AI identity an emerging concern for websites and applications. They are no longer interacting only with humans and traditiona
As threat actors increasingly use AI to accelerate and develop cyberattacks, enterprise defenders need to rely on both AI and a critical defender’s advantage: Business context that only you possess. E
Networking and security services provider GTT Communications Inc. today launched GTT Defense Halo, a network defense platform that uses artificial intelligence to hunt for threats on enterprise networ
arXiv:2606.18363v2 Announce Type: replace Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodi
First 3 disposition results. Hi there! My name is Jerry and I recently built Enclosure, e deterministic environment for testing LLMs. It's a simulated office enfironment https://github.com/openconstru
arXiv:2609.32660v1 Announce Type: new Abstract: Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns
OpenAI announced the launch of **dots**, an always‑on agent system powered by the GPT‑6 Astra model. According to OpenAI, dots are “remarkably capable” agents designed to handle a wide range of tasks
arXiv:2609.32874v1 Announce Type: cross Abstract: The first sentence of this abstract--and the introduction to these proceedings--was authored by a human, but the bulk of this document was generated b
Nvidia Corp. is extending the data processing unit from infrastructure offload to a broader security role across the artificial intelligence factory. The opportunity is to make agentic AI safer to ope
arXiv:2609.31714v1 Announce Type: new Abstract: Building omni-modal models with physical intelligence requires fine-grained supervision that captures physical evidence such as contact, support, deform
OpenAI Group PBC today rolled out reusable cloud environments for its Codex coding agent, giving developers a saved project configuration they can work from across devices. Announced at the company’s
Thanks to tcclaviger, vLLM now has expert RAM offloading support (link). This makes frontier models much more accessible on a local setup! I was able to run the original DeepSeek-V4-Flash-Vision-Exp o
arXiv:2606.19504v2 Announce Type: replace Abstract: Recent advancements in Resistive Force Theory (RFT) enable approximation of ground reaction forces for locomotion in sand without the computational
arXiv:2609.35501v1 Announce Type: cross Abstract: Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hyp
arXiv:2609.33237v1 Announce Type: new Abstract: Paired video-action demonstrations enable autonomous surgical behavior, but such data is scarce: robots perform roughly 1% of surgeries, while video-onl
Per-token pricing was the best thing to happen to enterprises looking to experiment with artificial intelligence, but it may be the worst thing for AI in production. That’s the quandary at the center
arXiv:2609.30297v1 Announce Type: cross Abstract: Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g
arXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to
arXiv:2609.30514v1 Announce Type: cross Abstract: Voice agents are increasingly deployed in workflows where failed interactions can affect transactions, access, and other consequential outcomes, creat
arXiv:2603.05069v3 Announce Type: replace Abstract: Personal AI agents face a deployment paradox on mobile: persistent background execution drains the battery and conflicts with platform background li
arXiv:2609.30279v1 Announce Type: new Abstract: Understanding the features captured by the hidden layers of neural networks is a fundamental challenge in machine learning, despite their widespread suc
arXiv:2609.30864v1 Announce Type: cross Abstract: Black-box On-Policy Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not token p
arXiv:2609.30657v1 Announce Type: cross Abstract: Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into t
arXiv:2609.31524v1 Announce Type: new Abstract: Surgical scene understanding is critical for computer-assisted intervention, yet laparoscopic cholecystectomy remains challenged by the complex anatomy
arXiv:2609.30614v1 Announce Type: cross Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM
arXiv:2609.30604v1 Announce Type: cross Abstract: Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, mul
We’re partnering with Nvidia and 100+ industry partners to build infrastructure that contains rogue AI agents. In this research, we gave 9 AI models root access inside SPACE and told them to break out
On Friday I gave the closing keynote at the WeAreDevelopers World Congress North America in San Jose. I tied together the key trends from the past year into a chronological exploration of everything t
Disclosure: I’m one of the authors of VeriLoop E2, a 27B model post-trained from Qwen3.8-27B. The weights are Apache-2.0; the harness we evaluate it in is not open source (details at the bottom). This
I posted an updated GPT-OSS template a couple of months ago, which was based on Unsloth's version. It turns out that both Unsloth's version (and, thus, mine) contain a very serious bug that can degrad